{"total":52,"rows":[{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2501.15891","title":"Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks","created":"2025-01-27","cited_by_count":63,"area":null},{"id":"2502.14546","title":"Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks","created":"2025-02-20","cited_by_count":53,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2405.20131","title":"Language Models Need Inductive Biases to Count Inductively","created":"2024-05-30","cited_by_count":25,"area":null},{"id":"2405.20671","title":"Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2406.10322","title":"LieRE: Lie Rotational Positional Encodings","created":"2024-06-14","cited_by_count":18,"area":null},{"id":"2502.11075","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","created":"2025-02-16","cited_by_count":14,"area":null},{"id":"2506.09251","title":"Extrapolation by Association: Length Generalization Transfer in Transformers","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2505.14172","title":"The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2506.23869","title":"Scaling Self-Supervised Representation Learning for Symbolic Piano Performance","created":"2025-06-30","cited_by_count":9,"area":null},{"id":"2509.04905","title":"Revolution or Hype? Seeking the Limits of Large Models in Hardware Design","created":"2025-09-05","cited_by_count":9,"area":null},{"id":"2409.17391","title":"Scaling Behavior for Large Language Models regarding Numeral Systems: An Example using Pythia","created":"2024-09-25","cited_by_count":8,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2510.27015","title":"Quantitative Bounds for Length Generalization in Transformers","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2406.15275","title":"How language models extrapolate outside the training data: A case study in Textualized Gridworld","created":"2024-06-21","cited_by_count":7,"area":null},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2510.06824","title":"Efficient numeracy in language models through single-token number embeddings","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2506.01734","title":"Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2410.01600","title":"ENTP: Encoder-only Next Token Prediction","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.19353","title":"Interleaving Text and Number Embeddings to Solve Mathemathics Problems","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2411.05943","title":"Quantifying artificial intelligence through algorithmic generalization","created":"2024-11-08","cited_by_count":5,"area":null},{"id":"2502.16763","title":"Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2406.17809","title":"Towards a Science Exocortex","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2605.05176","title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2410.08898","title":"Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2512.04963","title":"GeoPE:A Unified Geometric Positional Embedding for Structured Tensors","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2406.08272","title":"Learning interpretable positional encodings in transformers depends on initialization","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2506.23875","title":"Discovering Learning-Friendly Generation Orders for Sequential Computation","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2507.21257","title":"CompoST: A Benchmark for Analyzing the Ability of LLMs To Compositionally Interpret Questions in a QALD Setting","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2602.10416","title":"AI-rithmetic","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.26828","title":"Arithmetic OOD Failure Unfolds in Stages in Minimal GPTs","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2604.25166","title":"Training Transformers as a Universal Computer","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.26035","title":"Length Generalization with Log-Depth Recurrent Units","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2608.00418","title":"Making Transformers Logical","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2406.00075","title":"Arbitrary-Length Generalization for Addition in a Tiny Transformer","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2412.00129","title":"Scaling Particle Collision Data Analysis","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2506.00920","title":"Position as Probability: Self-Supervised Transformers that Think Past Their Training for Length Extrapolation","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2509.05394","title":"Reverse Browser: Vector-Image-to-Code Generator","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2510.04130","title":"On the Limitations and Capabilities of Position Embeddings for Length Generalization","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2512.07522","title":"LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.02867","title":"Training Language Models with homotokens Leads to Delayed Overfitting","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.12095","title":"Neural Isomorphic Fields: A Transformer-based Algebraic Numerical Embedding","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2605.08022","title":"Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.23044","title":"Prime Fourier Embeddings: A Principled Basis for Modular Arithmetic","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.01391","title":"How Should Transformers Encode Numeric Values in Electronic Health Records?","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.31067","title":"Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.25009","title":"Same Quantity, Different Answer: Numerical Representation Invariance in Language Models","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.16653","title":"Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}